© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 48969
    Prev
    Next
    INDEX
    Explanations

    hired or employed as

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    é¢ĺ主
    -0.13
    å°ı康
    -0.10
    çĶ¨åĵģ
    -0.09
    sembling
    -0.09
    ä¸Ģå¤ľ
    -0.09
    èijµ
    -0.09
     ÑĢÑĥк
    -0.09
    наÑĤ
    -0.09
    DataExchange
    -0.09
    utable
    -0.09
    POSITIVE LOGITS
    ensa
    0.09
    å¾Ĺèµ·
    0.09
    ÙĨÙĥ
    0.08
    imap
    0.08
    ç¿ķ
    0.08
     reinc
    0.08
    åĪ°è¿ĻéĩĮ
    0.08
    des
    0.08
    ITE
    0.07
    _tex
    0.07
    Activations Density 0.018%

    No Known Activations